agora inbox for [email protected]help / color / mirror / Atom feed
[PATCH] fix "Preserve relfilenodes" for pg_largeobject and its index 513+ messages / 2 participants [nested] [flat]
* [PATCH] fix "Preserve relfilenodes" for pg_largeobject and its index @ 2022-07-02 05:48 Justin Pryzby <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Justin Pryzby @ 2022-07-02 05:48 UTC (permalink / raw) An empty table is created by initdb, and the filenode was still pointing to that, so pg_largeobject was empty after binary upgrades. Test like: | ./tmp_install/usr/local/pgsql/bin/initdb --no-sync -D pg15b1.dat -k | ./tmp_install/usr/local/pgsql/bin/postgres -D pg15b1.dat -c logging_collector=no -p 5678 -k /tmp& | psql -h /tmp postgres -p 5678 -c '\lo_import /etc/shells' -c 'VACUUM FULL pg_largeobject' | rm -fr pg15b2.dat && ./tmp_install/usr/local/pgsql/bin/initdb --no-sync -k -D pg15b2.dat && ./tmp_install/usr/local/pgsql/bin/pg_upgrade -d pg15b1.dat -D pg15b2.dat -b ./tmp_install/usr/local/pgsql/bin | ./tmp_install/usr/local/pgsql/bin/postgres -D pg15b2.dat -c logging_collector=no -p 5678 -k /tmp& See also: 9a974cbcba005256a19991203583a94b4f9a21a9 https://www.postgresql.org/message-id/20210601140949.GC22012%40momjian.us https://www.postgresql.org/message-id/20220701231413.GI13040%40telsasoft.com --- src/bin/pg_dump/pg_dump.c | 37 ++++++++------ src/bin/pg_upgrade/relfilenumber.c | 68 +++++++++++++++++++++++--- src/bin/pg_upgrade/t/002_pg_upgrade.pl | 2 + 3 files changed, 86 insertions(+), 21 deletions(-) diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c index 227cdca2e2d..06d436f2f34 100644 --- a/src/bin/pg_dump/pg_dump.c +++ b/src/bin/pg_dump/pg_dump.c @@ -3135,7 +3135,7 @@ dumpDatabase(Archive *fout) /* * pg_largeobject comes from the old system intact, so set its - * relfrozenxids and relminmxids. + * relfrozenxids, relminmxids and relfilenode. */ if (dopt->binary_upgrade) { @@ -3143,34 +3143,41 @@ dumpDatabase(Archive *fout) PQExpBuffer loFrozenQry = createPQExpBuffer(); PQExpBuffer loOutQry = createPQExpBuffer(); int i_relfrozenxid, + i_relfilenode, + i_oid, i_relminmxid; /* * pg_largeobject */ if (fout->remoteVersion >= 90300) - appendPQExpBuffer(loFrozenQry, "SELECT relfrozenxid, relminmxid\n" + appendPQExpBuffer(loFrozenQry, "SELECT relfrozenxid, relminmxid, relfilenode, oid\n" "FROM pg_catalog.pg_class\n" - "WHERE oid = %u;\n", - LargeObjectRelationId); + "WHERE oid IN (%u, %u);\n", + LargeObjectRelationId, LargeObjectLOidPNIndexId); else - appendPQExpBuffer(loFrozenQry, "SELECT relfrozenxid, 0 AS relminmxid\n" + appendPQExpBuffer(loFrozenQry, "SELECT relfrozenxid, 0 AS relminmxid, relfilenode, oid\n" "FROM pg_catalog.pg_class\n" - "WHERE oid = %u;\n", - LargeObjectRelationId); + "WHERE oid IN (%u, %u);\n", + LargeObjectRelationId, LargeObjectLOidPNIndexId); - lo_res = ExecuteSqlQueryForSingleRow(fout, loFrozenQry->data); + lo_res = ExecuteSqlQuery(fout, loFrozenQry->data, PGRES_TUPLES_OK); i_relfrozenxid = PQfnumber(lo_res, "relfrozenxid"); i_relminmxid = PQfnumber(lo_res, "relminmxid"); + i_relfilenode = PQfnumber(lo_res, "relfilenode"); + i_oid = PQfnumber(lo_res, "oid"); + + appendPQExpBufferStr(loOutQry, "\n-- For binary upgrade, preserve values for pg_largeobject and its index\n"); + for (int i = 0; i < PQntuples(lo_res); ++i) + appendPQExpBuffer(loOutQry, "UPDATE pg_catalog.pg_class\n" + "SET relfrozenxid = '%u', relminmxid = '%u', relfilenode = '%u'\n" + "WHERE oid = %u;\n", + atooid(PQgetvalue(lo_res, i, i_relfrozenxid)), + atooid(PQgetvalue(lo_res, i, i_relminmxid)), + atooid(PQgetvalue(lo_res, i, i_relfilenode)), + atooid(PQgetvalue(lo_res, i, i_oid))); - appendPQExpBufferStr(loOutQry, "\n-- For binary upgrade, set pg_largeobject relfrozenxid and relminmxid\n"); - appendPQExpBuffer(loOutQry, "UPDATE pg_catalog.pg_class\n" - "SET relfrozenxid = '%u', relminmxid = '%u'\n" - "WHERE oid = %u;\n", - atooid(PQgetvalue(lo_res, 0, i_relfrozenxid)), - atooid(PQgetvalue(lo_res, 0, i_relminmxid)), - LargeObjectRelationId); ArchiveEntry(fout, nilCatalogId, createDumpId(), ARCHIVE_OPTS(.tag = "pg_largeobject", .description = "pg_largeobject", diff --git a/src/bin/pg_upgrade/relfilenumber.c b/src/bin/pg_upgrade/relfilenumber.c index b3ad8209eca..0dd649aa0f5 100644 --- a/src/bin/pg_upgrade/relfilenumber.c +++ b/src/bin/pg_upgrade/relfilenumber.c @@ -13,9 +13,13 @@ #include "access/transam.h" #include "catalog/pg_class_d.h" +#include "catalog/pg_largeobject_d.h" #include "pg_upgrade.h" -static void transfer_single_new_db(FileNameMap *maps, int size, char *old_tablespace); +static void transfer_single_new_db(FileNameMap *maps, int size, char *old_tablespace, + bool *has_lotable, bool *has_loindex); +static void remove_stray_largeobject_files(DbInfo *new_db, bool has_lotable, + bool has_loindex); static void transfer_relfile(FileNameMap *map, const char *suffix, bool vm_must_add_frozenbit); @@ -98,6 +102,8 @@ transfer_all_new_dbs(DbInfoArr *old_db_arr, DbInfoArr *new_db_arr, *new_db = NULL; FileNameMap *mappings; int n_maps; + bool has_lotable = false; + bool has_loindex = false; /* * Advance past any databases that exist in the new cluster but not in @@ -117,22 +123,66 @@ transfer_all_new_dbs(DbInfoArr *old_db_arr, DbInfoArr *new_db_arr, mappings = gen_db_file_maps(old_db, new_db, &n_maps, old_pgdata, new_pgdata); - if (n_maps) - { - transfer_single_new_db(mappings, n_maps, old_tablespace); - } + transfer_single_new_db(mappings, n_maps, old_tablespace, + &has_lotable, &has_loindex); + + /* + * Remove the original pg_largeobject files created by initdb if they + * exist in the new cluster with different relfilenodes. This avoids + * leaving behind stray files unassociated with any relation. + */ + remove_stray_largeobject_files(new_db, has_lotable, has_loindex); + /* We allocate something even for n_maps == 0 */ pg_free(mappings); } } +/* + * If there's no relation in the cluster whose relfilenode is the OID of the + * largeobject table/index, then remove the stray file. It ought to have a + * single segment and fork. + */ +static void +remove_stray_largeobject_files(DbInfo *new_db, bool has_lotable, + bool has_loindex) +{ + char prefix[MAXPGPATH]; + char largeobj_file[MAXPGPATH]; + + if (new_db->db_tablespace[0] != '\0') + snprintf(prefix, sizeof(prefix), "%s/%s/%u", + new_db->db_tablespace, new_cluster.tablespace_suffix, + new_db->db_oid); + else + snprintf(prefix, sizeof(prefix), "%s/base/%u", + new_cluster.pgdata, new_db->db_oid); + + if (!has_lotable) + { + snprintf(largeobj_file, sizeof(largeobj_file), "%s/%u", + prefix, LargeObjectRelationId); + if (unlink(largeobj_file) != 0) + pg_fatal("Unable to remove %s.\n", largeobj_file); + } + + if (!has_loindex) + { + snprintf(largeobj_file, sizeof(largeobj_file), "%s/%u", + prefix, LargeObjectLOidPNIndexId); + if (unlink(largeobj_file) != 0) + pg_fatal("Unable to remove %s.\n", largeobj_file); + } +} + /* * transfer_single_new_db() * * create links for mappings stored in "maps" array. */ static void -transfer_single_new_db(FileNameMap *maps, int size, char *old_tablespace) +transfer_single_new_db(FileNameMap *maps, int size, char *old_tablespace, + bool *has_lotable, bool *has_loindex) { int mapnum; bool vm_must_add_frozenbit = false; @@ -146,6 +196,12 @@ transfer_single_new_db(FileNameMap *maps, int size, char *old_tablespace) for (mapnum = 0; mapnum < size; mapnum++) { + /* Keep track of whether a filenode matches the OID */ + if (maps[mapnum].relfilenumber == LargeObjectRelationId) + *has_lotable = true; + if (maps[mapnum].relfilenumber == LargeObjectLOidPNIndexId) + *has_loindex = true; + if (old_tablespace == NULL || strcmp(maps[mapnum].old_tablespace, old_tablespace) == 0) { diff --git a/src/bin/pg_upgrade/t/002_pg_upgrade.pl b/src/bin/pg_upgrade/t/002_pg_upgrade.pl index 2f9b13bf0ae..9ed48c4e06a 100644 --- a/src/bin/pg_upgrade/t/002_pg_upgrade.pl +++ b/src/bin/pg_upgrade/t/002_pg_upgrade.pl @@ -208,6 +208,8 @@ if (defined($ENV{oldinstall})) } } +$oldnode->safe_psql("regression", "VACUUM FULL pg_largeobject;"); + # In a VPATH build, we'll be started in the source directory, but we want # to run pg_upgrade in the build directory so that any files generated finish # in it, like delete_old_cluster.{sh,bat}. -- 2.17.1 --m+utxuhC6KVTvgNz-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/6] Use background worker to do logical decoding. @ 2026-01-08 16:47 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-01-08 16:47 UTC (permalink / raw) If the backend performing REPACK (CONCURRENTLY) does both data copying and logical decoding, it has to "travel in time" back and forth and therefore it has to invalidate system caches quite a few times. (The copying and the decoding work with different catalog snapshots.) As the decoding worker has separate caches, the switching is not necessary. Without the worker, it'd also be difficult to switch between potentiallly long running tasks like index build and WAL decoding. (No decoding during that time at all can suspend archiving / recycling of WAL segments for some time, which in turn may result in full disk.) Another problem is that, after having acquired AccessExclusiveLock (in order to swap the files), the backend needs to both decode and apply the data changes that took place while it was waiting for the lock. With the decoding worker, the decoding runs all the time, so the backend only needs to apply the changes. This can reduce the time the exclusive lock is held for. Note that the code added in order to handle ERRORs in the background worker almost duplicates the existing code that does the same for other types of workers (See ProcessParallelMessages() and ProcessParallelApplyMessages()). Refactoring of the existing code might be useful, to reduce the duplication. --- src/backend/access/heap/heapam_handler.c | 44 - src/backend/commands/cluster.c | 1174 +++++++++++++---- src/backend/libpq/pqmq.c | 5 + src/backend/postmaster/bgworker.c | 4 + src/backend/replication/logical/logical.c | 6 +- .../pgoutput_repack/pgoutput_repack.c | 54 +- src/backend/storage/ipc/procsignal.c | 4 + src/backend/tcop/postgres.c | 4 + .../utils/activity/wait_event_names.txt | 2 + src/include/access/tableam.h | 7 +- src/include/commands/cluster.h | 71 +- src/include/storage/procsignal.h | 1 + src/tools/pgindent/typedefs.list | 4 +- 13 files changed, 979 insertions(+), 401 deletions(-) diff --git a/src/backend/access/heap/heapam_handler.c b/src/backend/access/heap/heapam_handler.c index 3526b6adcb5..475c536ce43 100644 --- a/src/backend/access/heap/heapam_handler.c +++ b/src/backend/access/heap/heapam_handler.c @@ -33,7 +33,6 @@ #include "catalog/index.h" #include "catalog/storage.h" #include "catalog/storage_xlog.h" -#include "commands/cluster.h" #include "commands/progress.h" #include "executor/executor.h" #include "miscadmin.h" @@ -688,7 +687,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, Relation OldIndex, bool use_sort, TransactionId OldestXmin, Snapshot snapshot, - LogicalDecodingContext *decoding_ctx, TransactionId *xid_cutoff, MultiXactId *multi_cutoff, double *num_tuples, @@ -710,7 +708,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, BufferHeapTupleTableSlot *hslot; BlockNumber prev_cblock = InvalidBlockNumber; bool concurrent = snapshot != NULL; - XLogRecPtr end_of_wal_prev = GetFlushRecPtr(NULL); /* Remember if it's a system catalog */ is_system_catalog = IsSystemRelation(OldHeap); @@ -957,31 +954,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, ct_val[1] = *num_tuples; pgstat_progress_update_multi_param(2, ct_index, ct_val); } - - /* - * Process the WAL produced by the load, as well as by other - * transactions, so that the replication slot can advance and WAL does - * not pile up. Use wal_segment_size as a threshold so that we do not - * introduce the decoding overhead too often. - * - * Of course, we must not apply the changes until the initial load has - * completed. - * - * Note that our insertions into the new table should not be decoded - * as we (intentionally) do not write the logical decoding specific - * information to WAL. - */ - if (concurrent) - { - XLogRecPtr end_of_wal; - - end_of_wal = GetFlushRecPtr(NULL); - if ((end_of_wal - end_of_wal_prev) > wal_segment_size) - { - repack_decode_concurrent_changes(decoding_ctx, end_of_wal); - end_of_wal_prev = end_of_wal; - } - } } if (indexScan != NULL) @@ -1027,22 +999,6 @@ heapam_relation_copy_for_cluster(Relation OldHeap, Relation NewHeap, /* Report n_tuples */ pgstat_progress_update_param(PROGRESS_REPACK_HEAP_TUPLES_INSERTED, n_tuples); - - /* - * Try to keep the amount of not-yet-decoded WAL small, like - * above. - */ - if (concurrent) - { - XLogRecPtr end_of_wal; - - end_of_wal = GetFlushRecPtr(NULL); - if ((end_of_wal - end_of_wal_prev) > wal_segment_size) - { - repack_decode_concurrent_changes(decoding_ctx, end_of_wal); - end_of_wal_prev = end_of_wal; - } - } } tuplesort_end(tuplesort); diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index c3feb0c3de4..5232fbfb57d 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -12,12 +12,13 @@ * In concurrent mode, we lock the table with only ShareUpdateExclusiveLock, * then do an initial copy as above. However, while the tuples are being * copied, concurrent transactions could modify the table. To cope with those - * changes, we rely on logical decoding to obtain them from WAL. The changes - * are accumulated in a tuplestore. Once the initial copy is complete, we - * read the changes from the tuplestore and re-apply them on the new heap. - * Then we upgrade our ShareUpdateExclusiveLock to AccessExclusiveLock and - * swap the relfilenodes. This way, the time we hold a strong lock on the - * table is much reduced, and the bloat is eliminated. + * changes, we rely on logical decoding to obtain them from WAL. A bgworker + * consumes WAL while the initial copy is ongoing (to prevent excessive WAL + * from being reserved), and accumulates the changes in a file. Once the + * initial copy is complete, we read the changes from the file and re-apply + * them on the new heap. Then we upgrade our ShareUpdateExclusiveLock to + * AccessExclusiveLock and swap the relfilenodes. This way, the time we hold + * a strong lock on the table is much reduced, and the bloat is eliminated. * * There is hardly anything left of Paul Brown's original implementation... * @@ -45,6 +46,7 @@ #include "access/xlog_internal.h" #include "access/xloginsert.h" #include "access/xlogutils.h" +#include "access/xlogwait.h" #include "catalog/catalog.h" #include "catalog/dependency.h" #include "catalog/heap.h" @@ -61,6 +63,8 @@ #include "commands/tablecmds.h" #include "commands/vacuum.h" #include "executor/executor.h" +#include "libpq/pqformat.h" +#include "libpq/pqmq.h" #include "miscadmin.h" #include "optimizer/optimizer.h" #include "pgstat.h" @@ -71,6 +75,8 @@ #include "storage/ipc.h" #include "storage/lmgr.h" #include "storage/predicate.h" +#include "storage/procsignal.h" +#include "tcop/tcopprot.h" #include "utils/acl.h" #include "utils/fmgroids.h" #include "utils/guc.h" @@ -117,6 +123,12 @@ typedef struct IndexInsertState /* The WAL segment being decoded. */ static XLogSegNo repack_current_segment = 0; +/* + * The first file exported by the decoding worker must contain a snapshot, the + * following ones contain the data changes. + */ +#define WORKER_FILE_SNAPSHOT 0 + /* * Information needed to apply concurrent data changes. */ @@ -136,8 +148,113 @@ typedef struct ChangeDest /* Needed to update indexes of rel_dst. */ IndexInsertState *iistate; + + /* + * Sequential number of the file containing the changes. + * + * TODO This field makes the structure name less descriptive. Should we + * rename it, e.g. to ChangeApplyInfo? + */ + int file_seq; } ChangeDest; +/* + * Layout of shared memory used for communication between backend and the + * worker that performs logical decoding of data changes + */ +typedef struct DecodingWorkerShared +{ + /* Is the decoding initialized? */ + bool initialized; + + /* + * Once the worker has reached this LSN, it should close the current + * output file and either create a new one or exit, according to the field + * 'done'. If the value is InvalidXLogRecPtr, the worker should decode all + * the WAL available and keep checking this field. It is ok if the worker + * had already decoded records whose LSN is >= lsn_upto before this field + * has been set. + */ + XLogRecPtr lsn_upto; + + /* Exit after closing the current file? */ + bool done; + + /* The output is stored here. */ + SharedFileSet sfs; + + /* Number of the last file exported by the worker. */ + int last_exported; + + /* Synchronize access to the fields above. */ + slock_t mutex; + + /* Database to connect to. */ + Oid dbid; + + /* Role to connect as. */ + Oid roleid; + + /* Decode data changes of this relation. */ + Oid relid; + + /* The backend uses this to wait for the worker. */ + ConditionVariable cv; + + /* Info to signal the backend. */ + PGPROC *backend_proc; + pid_t backend_pid; + ProcNumber backend_proc_number; + + /* Error queue. */ + shm_mq *error_mq; + + /* + * Memory the queue is located int. + * + * For considerations on the value see the comments of + * PARALLEL_ERROR_QUEUE_SIZE. + */ +#define REPACK_ERROR_QUEUE_SIZE 16384 + char error_queue[FLEXIBLE_ARRAY_MEMBER]; +} DecodingWorkerShared; + +/* + * Generate worker's output file name. If relations of the same 'relid' happen + * to be processed at the same time, they must be from different databases and + * therefore different backends must be involved. (PID is already present in + * the fileset name.) + */ +static inline void +DecodingWorkerFileName(char *fname, Oid relid, uint32 seq) +{ + snprintf(fname, MAXPGPATH, "%u-%u", relid, seq); +} + +/* + * Backend-local information to control the decoding worker. + */ +typedef struct DecodingWorker +{ + /* The worker. */ + BackgroundWorkerHandle *handle; + + /* DecodingWorkerShared is in this segment. */ + dsm_segment *seg; + + /* Handle of the error queue. */ + shm_mq_handle *error_mqh; +} DecodingWorker; + +/* Pointer to currently running decoding worker. */ +static DecodingWorker *decoding_worker = NULL; + +/* + * Is there a message sent by a repack worker that the backend needs to + * receive? + */ +volatile sig_atomic_t RepackMessagePending = false; + static bool cluster_rel_recheck(RepackCommand cmd, Relation OldHeap, Oid indexOid, Oid userid, LOCKMODE lmode, int options); @@ -145,7 +262,7 @@ static void check_repack_concurrently_requirements(Relation rel); static void rebuild_relation(Relation OldHeap, Relation index, bool verbose, bool concurrent); static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex, - Snapshot snapshot, LogicalDecodingContext *decoding_ctx, + Snapshot snapshot, bool verbose, bool *pSwapToastByContent, TransactionId *pFreezeXid, @@ -158,12 +275,10 @@ static List *get_tables_to_repack_partitioned(RepackCommand cmd, static bool cluster_is_permitted_for_relation(RepackCommand cmd, Oid relid, Oid userid); -static void begin_concurrent_repack(Relation rel); -static void end_concurrent_repack(void); static LogicalDecodingContext *setup_logical_decoding(Oid relid); -static HeapTuple get_changed_tuple(char *change); -static void apply_concurrent_changes(RepackDecodingState *dstate, - ChangeDest *dest); +static bool decode_concurrent_changes(LogicalDecodingContext *ctx, + DecodingWorkerShared *shared); +static void apply_concurrent_changes(BufFile *file, ChangeDest *dest); static void apply_concurrent_insert(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); @@ -175,9 +290,9 @@ static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); -static void process_concurrent_changes(LogicalDecodingContext *decoding_ctx, - XLogRecPtr end_of_wal, - ChangeDest *dest); +static void process_concurrent_changes(XLogRecPtr end_of_wal, + ChangeDest *dest, + bool done); static IndexInsertState *get_index_insert_state(Relation relation, Oid ident_index_id, Relation *ident_index_p); @@ -187,7 +302,6 @@ static void free_index_insert_state(IndexInsertState *iistate); static void cleanup_logical_decoding(LogicalDecodingContext *ctx); static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Relation cl_index, - LogicalDecodingContext *decoding_ctx, TransactionId frozenXid, MultiXactId cutoffMulti); static List *build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes); @@ -197,6 +311,13 @@ static Relation process_single_relation(RepackStmt *stmt, ClusterParams *params); static Oid determine_clustered_index(Relation rel, bool usingindex, const char *indexname); +static void start_decoding_worker(Oid relid); +static void stop_decoding_worker(void); +static void repack_worker_internal(dsm_segment *seg); +static void export_initial_snapshot(Snapshot snapshot, + DecodingWorkerShared *shared); +static Snapshot get_initial_snapshot(DecodingWorker *worker); +static void ProcessRepackMessage(StringInfo msg); static const char *RepackCommandAsString(RepackCommand cmd); @@ -619,20 +740,20 @@ cluster_rel(RepackCommand cmd, Relation OldHeap, Oid indexOid, /* rebuild_relation does all the dirty work */ PG_TRY(); { - /* - * For concurrent processing, make sure that our logical decoding - * ignores data changes of other tables than the one we are - * processing. - */ - if (concurrent) - begin_concurrent_repack(OldHeap); - rebuild_relation(OldHeap, index, verbose, concurrent); } PG_FINALLY(); { if (concurrent) - end_concurrent_repack(); + { + /* + * Since during normal operation the worker was already asked to + * exit, stopping it explicitly is especially important on ERROR. + * However it still seems a good practice to make sure that the + * worker never survives the REPACK command. + */ + stop_decoding_worker(); + } } PG_END_TRY(); @@ -929,7 +1050,6 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, bool concurrent bool swap_toast_by_content; TransactionId frozenXid; MultiXactId cutoffMulti; - LogicalDecodingContext *decoding_ctx = NULL; Snapshot snapshot = NULL; #if USE_ASSERT_CHECKING LOCKMODE lmode; @@ -943,19 +1063,36 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, bool concurrent if (concurrent) { /* - * Prepare to capture the concurrent data changes. + * The worker needs to be member of the locking group we're the leader + * of. We ought to become the leader before the worker starts. The + * worker will join the group as soon as it starts. * - * Note that this call waits for all transactions with XID already - * assigned to finish. If some of those transactions is waiting for a - * lock conflicting with ShareUpdateExclusiveLock on our table (e.g. - * it runs CREATE INDEX), we can end up in a deadlock. Not sure this - * risk is worth unlocking/locking the table (and its clustering - * index) and checking again if its still eligible for REPACK - * CONCURRENTLY. + * This is to make sure that the deadlock described below is + * detectable by deadlock.c: if the worker waits for a transaction to + * complete and we are waiting for the worker output, then effectively + * we (i.e. this backend) are waiting for that transaction. */ - decoding_ctx = setup_logical_decoding(tableOid); + BecomeLockGroupLeader(); + + /* + * Start the worker that decodes data changes applied while we're + * copying the table contents. + * + * Note that the worker has to wait for all transactions with XID + * already assigned to finish. If some of those transactions is + * waiting for a lock conflicting with ShareUpdateExclusiveLock on our + * table (e.g. it runs CREATE INDEX), we can end up in a deadlock. + * Not sure this risk is worth unlocking/locking the table (and its + * clustering index) and checking again if its still eligible for + * REPACK CONCURRENTLY. + */ + start_decoding_worker(tableOid); + + /* + * Wait until the worker has the initial snapshot and retrieve it. + */ + snapshot = get_initial_snapshot(decoding_worker); - snapshot = SnapBuildInitialSnapshotForRepack(decoding_ctx->snapshot_builder); PushActiveSnapshot(snapshot); } @@ -980,7 +1117,7 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, bool concurrent NewHeap = table_open(OIDNewHeap, NoLock); /* Copy the heap data into the new table in the desired order */ - copy_table_data(NewHeap, OldHeap, index, snapshot, decoding_ctx, verbose, + copy_table_data(NewHeap, OldHeap, index, snapshot, verbose, &swap_toast_by_content, &frozenXid, &cutoffMulti); /* The historic snapshot won't be needed anymore. */ @@ -994,14 +1131,10 @@ rebuild_relation(Relation OldHeap, Relation index, bool verbose, bool concurrent { Assert(!swap_toast_by_content); rebuild_relation_finish_concurrent(NewHeap, OldHeap, index, - decoding_ctx, frozenXid, cutoffMulti); pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_FINAL_CLEANUP); - - /* Done with decoding. */ - cleanup_logical_decoding(decoding_ctx); } else { @@ -1172,8 +1305,7 @@ make_new_heap(Oid OIDOldHeap, Oid NewTableSpace, Oid NewAccessMethod, */ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex, - Snapshot snapshot, LogicalDecodingContext *decoding_ctx, - bool verbose, bool *pSwapToastByContent, + Snapshot snapshot, bool verbose, bool *pSwapToastByContent, TransactionId *pFreezeXid, MultiXactId *pCutoffMulti) { Relation relRelation; @@ -1334,7 +1466,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex, */ table_relation_copy_for_cluster(OldHeap, NewHeap, OldIndex, use_sort, cutoffs.OldestXmin, snapshot, - decoding_ctx, &cutoffs.FreezeLimit, &cutoffs.MultiXactCutoff, &num_tuples, &tups_vacuumed, @@ -2367,59 +2498,6 @@ RepackCommandAsString(RepackCommand cmd) return "???"; } - -/* - * Call this function before REPACK CONCURRENTLY starts to setup logical - * decoding. It makes sure that other users of the table put enough - * information into WAL. - * - * The point is that at various places we expect that the table we're - * processing is treated like a system catalog. For example, we need to be - * able to scan it using a "historic snapshot" anytime during the processing - * (as opposed to scanning only at the start point of the decoding, as logical - * replication does during initial table synchronization), in order to apply - * concurrent UPDATE / DELETE commands. - * - * Note that TOAST table needs no attention here as it's not scanned using - * historic snapshot. - */ -static void -begin_concurrent_repack(Relation rel) -{ - Oid toastrelid; - - /* - * Avoid logical decoding of other relations by this backend. The lock we - * have guarantees that the actual locator cannot be changed concurrently: - * TRUNCATE needs AccessExclusiveLock. - */ - Assert(CheckRelationLockedByMe(rel, ShareUpdateExclusiveLock, false)); - repacked_rel_locator = rel->rd_locator; - toastrelid = rel->rd_rel->reltoastrelid; - if (OidIsValid(toastrelid)) - { - Relation toastrel; - - /* Avoid logical decoding of other TOAST relations. */ - toastrel = table_open(toastrelid, AccessShareLock); - repacked_rel_toast_locator = toastrel->rd_locator; - table_close(toastrel, AccessShareLock); - } -} - -/* - * Call this when done with REPACK CONCURRENTLY. - */ -static void -end_concurrent_repack(void) -{ - /* - * Restore normal function of (future) logical decoding for this backend. - */ - repacked_rel_locator.relNumber = InvalidOid; - repacked_rel_toast_locator.relNumber = InvalidOid; -} - /* * Is this backend performing logical decoding on behalf of REPACK * (CONCURRENTLY) ? @@ -2484,9 +2562,10 @@ static LogicalDecodingContext * setup_logical_decoding(Oid relid) { Relation rel; - TupleDesc tupdesc; + Oid toastrelid; LogicalDecodingContext *ctx; - RepackDecodingState *dstate = palloc0_object(RepackDecodingState); + NameData slotname; + RepackDecodingState *dstate; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2494,21 +2573,21 @@ setup_logical_decoding(Oid relid) */ Assert(!TransactionIdIsValid(GetTopTransactionIdIfAny())); - /* - * A single backend should not execute multiple REPACK commands at a time, - * so use PID to make the slot unique. - */ - snprintf(NameStr(dstate->slotname), NAMEDATALEN, "repack_%d", MyProcPid); - /* * Check if we can use logical decoding. */ CheckSlotPermissions(); CheckLogicalDecodingRequirements(); - /* RS_TEMPORARY so that the slot gets cleaned up on ERROR. */ - ReplicationSlotCreate(NameStr(dstate->slotname), true, RS_TEMPORARY, - false, false, false); + /* + * A single backend should not execute multiple REPACK commands at a time, + * so use PID to make the slot unique. + * + * RS_TEMPORARY so that the slot gets cleaned up on ERROR. + */ + snprintf(NameStr(slotname), NAMEDATALEN, "repack_%d", MyProcPid); + ReplicationSlotCreate(NameStr(slotname), true, RS_TEMPORARY, false, false, + false); /* * Neither prepare_write nor do_write callback nor update_progress is @@ -2530,104 +2609,109 @@ setup_logical_decoding(Oid relid) DecodingContextFindStartpoint(ctx); + /* + * decode_concurrent_changes() needs non-blocking callback. + */ + ctx->reader->routine.page_read = read_local_xlog_page_no_wait; + + /* + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. + */ + ctx->reader->private_data = MemoryContextAllocZero(ctx->context, + sizeof(ReadLocalXLogPageNoWaitPrivate)); + + /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); + /* + * Initialize repack_current_segment so that we can notice WAL segment + * boundaries. + */ XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - /* - * Setup structures to store decoded changes. - */ + dstate = palloc0_object(RepackDecodingState); dstate->relid = relid; - dstate->tstore = tuplestore_begin_heap(false, false, - maintenance_work_mem); - /* Caller should already have the table locked. */ - rel = table_open(relid, NoLock); - tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); - dstate->tupdesc = tupdesc; - table_close(rel, NoLock); + /* + * Tuple descriptor may be needed to flatten a tuple before we write it to + * a file. A copy is needed because the decoding worker invalidates system + * caches before it starts to do the actual work. + */ + rel = table_open(relid, AccessShareLock); + dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); - /* Initialize the descriptor to store the changes ... */ - dstate->tupdesc_change = CreateTemplateTupleDesc(1); + /* Avoid logical decoding of other relations. */ + repacked_rel_locator = rel->rd_locator; + toastrelid = rel->rd_rel->reltoastrelid; + if (OidIsValid(toastrelid)) + { + Relation toastrel; - TupleDescInitEntry(dstate->tupdesc_change, 1, NULL, BYTEAOID, -1, 0); - /* ... as well as the corresponding slot. */ - dstate->tsslot = MakeSingleTupleTableSlot(dstate->tupdesc_change, - &TTSOpsMinimalTuple); + /* Avoid logical decoding of other TOAST relations. */ + toastrel = table_open(toastrelid, AccessShareLock); + repacked_rel_toast_locator = toastrel->rd_locator; + table_close(toastrel, AccessShareLock); + } + table_close(rel, AccessShareLock); - dstate->resowner = ResourceOwnerCreate(CurrentResourceOwner, - "logical decoding"); + /* The file will be set as soon as we have it opened. */ + dstate->file = NULL; ctx->output_writer_private = dstate; + return ctx; } /* - * Retrieve tuple from ConcurrentChange structure. + * Decode logical changes from the WAL sequence and store them to a file. * - * The input data starts with the structure but it might not be appropriately - * aligned. - */ -static HeapTuple -get_changed_tuple(char *change) -{ - HeapTupleData tup_data; - HeapTuple result; - char *src; - - /* - * Ensure alignment before accessing the fields. (This is why we can't use - * heap_copytuple() instead of this function.) - */ - src = change + offsetof(ConcurrentChange, tup_data); - memcpy(&tup_data, src, sizeof(HeapTupleData)); - - result = (HeapTuple) palloc(HEAPTUPLESIZE + tup_data.t_len); - memcpy(result, &tup_data, sizeof(HeapTupleData)); - result->t_data = (HeapTupleHeader) ((char *) result + HEAPTUPLESIZE); - src = change + SizeOfConcurrentChange; - memcpy(result->t_data, src, result->t_len); - - return result; -} - -/* - * Decode logical changes from the WAL sequence up to end_of_wal. + * If true is returned, there is no more work for the worker. */ -void -repack_decode_concurrent_changes(LogicalDecodingContext *ctx, - XLogRecPtr end_of_wal) +static bool +decode_concurrent_changes(LogicalDecodingContext *ctx, + DecodingWorkerShared *shared) { RepackDecodingState *dstate; - ResourceOwner resowner_old; + XLogRecPtr lsn_upto; + bool done; + char fname[MAXPGPATH]; dstate = (RepackDecodingState *) ctx->output_writer_private; - resowner_old = CurrentResourceOwner; - CurrentResourceOwner = dstate->resowner; - PG_TRY(); + /* Open the output file. */ + DecodingWorkerFileName(fname, shared->relid, shared->last_exported + 1); + dstate->file = BufFileCreateFileSet(&shared->sfs.fs, fname); + + SpinLockAcquire(&shared->mutex); + lsn_upto = shared->lsn_upto; + done = shared->done; + SpinLockRelease(&shared->mutex); + + while (true) { - while (ctx->reader->EndRecPtr < end_of_wal) - { - XLogRecord *record; - XLogSegNo segno_new; - char *errm = NULL; - XLogRecPtr end_lsn; + XLogRecord *record; + XLogSegNo segno_new; + char *errm = NULL; + XLogRecPtr end_lsn; - record = XLogReadRecord(ctx->reader, &errm); - if (errm) - elog(ERROR, "%s", errm); + CHECK_FOR_INTERRUPTS(); - if (record != NULL) - LogicalDecodingProcessRecord(ctx, ctx->reader); + record = XLogReadRecord(ctx->reader, &errm); + if (record) + { + LogicalDecodingProcessRecord(ctx, ctx->reader); /* * If WAL segment boundary has been crossed, inform the decoding - * system that the catalog_xmin can advance. (We can confirm more - * often, but a filling a single WAL segment should not take much - * time.) + * system that the catalog_xmin can advance. + * + * TODO Does it make sense to confirm more often? Segment size + * seems appropriate for restart_lsn (because less than a segment + * cannot be recycled anyway), however more frequent checks might + * be beneficial for catalog_xmin. */ end_lsn = ctx->reader->EndRecPtr; XLByteToSeg(end_lsn, segno_new, wal_segment_size); @@ -2638,80 +2722,137 @@ repack_decode_concurrent_changes(LogicalDecodingContext *ctx, (uint32) (end_lsn >> 32), (uint32) end_lsn); repack_current_segment = segno_new; } + } + else + { + ReadLocalXLogPageNoWaitPrivate *priv; - CHECK_FOR_INTERRUPTS(); + if (errm) + ereport(ERROR, (errmsg("%s", errm))); + + /* + * In the decoding loop we do not want to get blocked when there + * is no more WAL available, otherwise the loop would become + * uninterruptible. + */ + priv = (ReadLocalXLogPageNoWaitPrivate *) + ctx->reader->private_data; + if (priv->end_of_wal) + /* Do not miss the end of WAL condition next time. */ + priv->end_of_wal = false; + else + ereport(ERROR, (errmsg("could not read WAL record"))); + } + + /* + * Whether we could read new record or not, keep checking if + * 'lsn_upto' was specified. + */ + if (XLogRecPtrIsInvalid(lsn_upto)) + { + SpinLockAcquire(&shared->mutex); + lsn_upto = shared->lsn_upto; + /* 'done' should be set at the same time as 'lsn_upto' */ + done = shared->done; + SpinLockRelease(&shared->mutex); + } + if (!XLogRecPtrIsInvalid(lsn_upto) && + ctx->reader->EndRecPtr >= lsn_upto) + break; + + if (record == NULL) + { + int64 timeout = 0; + WaitLSNResult res; + + /* + * Before we retry reading, wait until new WAL is flushed. + * + * There is a race condition such that the backend executing + * REPACK determines 'lsn_upto', but before it sets the shared + * variable, we reach the end of WAL. In that case we'd need to + * wait until the next WAL flush (unrelated to REPACK). Although + * that should not be a problem in a busy system, it might be + * noticeable in other cases, including regression tests (which + * are not necessarily executed in parallel). Therefore it makes + * sense to use timeout. + * + * If lsn_upto is valid, WAL records having LSN lower than that + * should already have been flushed to disk. + */ + if (XLogRecPtrIsInvalid(lsn_upto)) + timeout = 100L; + res = WaitForLSN(WAIT_LSN_TYPE_PRIMARY_FLUSH, + ctx->reader->EndRecPtr + 1, + timeout); + if (res != WAIT_LSN_RESULT_SUCCESS && + res != WAIT_LSN_RESULT_TIMEOUT) + ereport(ERROR, (errmsg("waiting for WAL failed"))); } - InvalidateSystemCaches(); - CurrentResourceOwner = resowner_old; - } - PG_CATCH(); - { - /* clear all timetravel entries */ - InvalidateSystemCaches(); - CurrentResourceOwner = resowner_old; - PG_RE_THROW(); } - PG_END_TRY(); + + /* + * Close the file so we can make it available to the backend. + */ + BufFileClose(dstate->file); + dstate->file = NULL; + SpinLockAcquire(&shared->mutex); + shared->lsn_upto = InvalidXLogRecPtr; + shared->last_exported++; + SpinLockRelease(&shared->mutex); + ConditionVariableSignal(&shared->cv); + + return done; } /* * Apply changes stored in 'file'. */ static void -apply_concurrent_changes(RepackDecodingState *dstate, ChangeDest *dest) +apply_concurrent_changes(BufFile *file, ChangeDest *dest) { + char kind; + uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; HeapTuple tup_old = NULL; - if (dstate->nchanges == 0) - return; - /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ - index_slot = MakeSingleTupleTableSlot(dstate->tupdesc, &TTSOpsHeapTuple); + index_slot = MakeSingleTupleTableSlot(RelationGetDescr(rel), + &TTSOpsHeapTuple); /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); - while (tuplestore_gettupleslot(dstate->tstore, true, false, - dstate->tsslot)) + while (true) { - bool shouldFree; - HeapTuple tup_change, - tup, + size_t nread; + HeapTuple tup, tup_exist; - char *change_raw, - *src; - ConcurrentChange change; - bool isnull[1]; - Datum values[1]; CHECK_FOR_INTERRUPTS(); - /* Get the change from the single-column tuple. */ - tup_change = ExecFetchSlotHeapTuple(dstate->tsslot, false, &shouldFree); - heap_deform_tuple(tup_change, dstate->tupdesc_change, values, isnull); - Assert(!isnull[0]); - - /* Make sure we access aligned data. */ - change_raw = (char *) DatumGetByteaP(values[0]); - src = (char *) VARDATA(change_raw); - memcpy(&change, src, SizeOfConcurrentChange); + nread = BufFileReadMaybeEOF(file, &kind, 1, true); + /* Are we done with the file? */ + if (nread == 0) + break; - /* - * Extract the tuple from the change. The tuple is copied here because - * it might be assigned to 'tup_old', in which case it needs to - * survive into the next iteration. - */ - tup = get_changed_tuple(src); + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(dest->rel); - if (change.kind == CHANGE_UPDATE_OLD) + if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); tup_old = tup; } - else if (change.kind == CHANGE_INSERT) + else if (kind == CHANGE_INSERT) { Assert(tup_old == NULL); @@ -2719,12 +2860,11 @@ apply_concurrent_changes(RepackDecodingState *dstate, ChangeDest *dest) pfree(tup); } - else if (change.kind == CHANGE_UPDATE_NEW || - change.kind == CHANGE_DELETE) + else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { HeapTuple tup_key; - if (change.kind == CHANGE_UPDATE_NEW) + if (kind == CHANGE_UPDATE_NEW) { tup_key = tup_old != NULL ? tup_old : tup; } @@ -2741,7 +2881,7 @@ apply_concurrent_changes(RepackDecodingState *dstate, ChangeDest *dest) if (tup_exist == NULL) elog(ERROR, "failed to find target tuple"); - if (change.kind == CHANGE_UPDATE_NEW) + if (kind == CHANGE_UPDATE_NEW) apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); else @@ -2756,26 +2896,19 @@ apply_concurrent_changes(RepackDecodingState *dstate, ChangeDest *dest) pfree(tup); } else - elog(ERROR, "unrecognized kind of change: %d", change.kind); + elog(ERROR, "unrecognized kind of change: %d", kind); /* * If a change was applied now, increment CID for next writes and * update the snapshot so it sees the changes we've applied so far. */ - if (change.kind != CHANGE_UPDATE_OLD) + if (kind != CHANGE_UPDATE_OLD) { CommandCounterIncrement(); UpdateActiveSnapshotCommandId(); } - - /* TTSOpsMinimalTuple has .get_heap_tuple==NULL. */ - Assert(shouldFree); - pfree(tup_change); } - tuplestore_clear(dstate->tstore); - dstate->nchanges = 0; - /* Cleanup. */ ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); @@ -2954,25 +3087,59 @@ find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, } /* - * Decode and apply concurrent changes. + * Decode and apply concurrent changes, up to (and including) the record whose + * LSN is 'end_of_wal'. */ static void -process_concurrent_changes(LogicalDecodingContext *decoding_ctx, - XLogRecPtr end_of_wal, ChangeDest *dest) +process_concurrent_changes(XLogRecPtr end_of_wal, ChangeDest *dest, bool done) { - RepackDecodingState *dstate; + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; pgstat_progress_update_param(PROGRESS_REPACK_PHASE, PROGRESS_REPACK_PHASE_CATCH_UP); - dstate = (RepackDecodingState *) decoding_ctx->output_writer_private; + /* Ask the worker for the file. */ + shared = (DecodingWorkerShared *) dsm_segment_address(decoding_worker->seg); + SpinLockAcquire(&shared->mutex); + shared->lsn_upto = end_of_wal; + shared->done = done; + SpinLockRelease(&shared->mutex); - repack_decode_concurrent_changes(decoding_ctx, end_of_wal); + /* + * The worker needs to finish processing of the current WAL record. Even + * if it's idle, it'll need to close the output file. Thus we're likely to + * wait, so prepare for sleep. + */ + ConditionVariablePrepareToSleep(&shared->cv); + for (;;) + { + int last_exported; - if (dstate->nchanges == 0) - return; + SpinLockAcquire(&shared->mutex); + last_exported = shared->last_exported; + SpinLockRelease(&shared->mutex); + + /* + * Has the worker exported the file we are waiting for? + */ + if (last_exported == dest->file_seq) + break; + + ConditionVariableSleep(&shared->cv, WAIT_EVENT_REPACK_WORKER_EXPORT); + } + ConditionVariableCancelSleep(); - apply_concurrent_changes(dstate, dest); + /* Open the file. */ + DecodingWorkerFileName(fname, shared->relid, dest->file_seq); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); + apply_concurrent_changes(file, dest); + + BufFileClose(file); + + /* Get ready for the next file. */ + dest->file_seq++; } /* @@ -3098,15 +3265,10 @@ cleanup_logical_decoding(LogicalDecodingContext *ctx) dstate = (RepackDecodingState *) ctx->output_writer_private; - ExecDropSingleTupleTableSlot(dstate->tsslot); - FreeTupleDesc(dstate->tupdesc_change); FreeTupleDesc(dstate->tupdesc); - tuplestore_end(dstate->tstore); - FreeDecodingContext(ctx); - ReplicationSlotRelease(); - ReplicationSlotDrop(NameStr(dstate->slotname), false); + ReplicationSlotDropAcquired(); pfree(dstate); } @@ -3121,7 +3283,6 @@ cleanup_logical_decoding(LogicalDecodingContext *ctx) static void rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, Relation cl_index, - LogicalDecodingContext *decoding_ctx, TransactionId frozenXid, MultiXactId cutoffMulti) { @@ -3204,6 +3365,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, &chgdst.ident_index); chgdst.ident_key = build_identity_key(ident_idx_new, OldHeap, &chgdst.ident_key_nentries); + chgdst.file_seq = WORKER_FILE_SNAPSHOT + 1; /* * During testing, wait for another backend to perform concurrent data @@ -3225,7 +3387,7 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, * hold AccessExclusiveLock. (Quite some amount of WAL could have been * written during the data copying and index creation.) */ - process_concurrent_changes(decoding_ctx, end_of_wal, &chgdst); + process_concurrent_changes(end_of_wal, &chgdst, false); /* * Acquire AccessExclusiveLock on the table, its TOAST relation (if there @@ -3319,8 +3481,11 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, XLogFlush(wal_insert_ptr); end_of_wal = GetFlushRecPtr(NULL); - /* Apply the concurrent changes again. */ - process_concurrent_changes(decoding_ctx, end_of_wal, &chgdst); + /* + * Apply the concurrent changes again. Indicate that the decoding worker + * won't be needed anymore. + */ + process_concurrent_changes(end_of_wal, &chgdst, true); /* Remember info about rel before closing OldHeap */ relpersistence = OldHeap->rd_rel->relpersistence; @@ -3430,3 +3595,510 @@ build_new_indexes(Relation NewHeap, Relation OldHeap, List *OldIndexes) return result; } + +/* + * Try to start a background worker to perform logical decoding of data + * changes applied to relation while REPACK CONCURRENTLY is copying its + * contents to a new table. + */ +static void +start_decoding_worker(Oid relid) +{ + Size size; + dsm_segment *seg; + DecodingWorkerShared *shared; + shm_mq *mq; + shm_mq_handle *mqh; + BackgroundWorker bgw; + + /* Setup shared memory. */ + size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); + seg = dsm_create(size, 0); + shared = (DecodingWorkerShared *) dsm_segment_address(seg); + shared->lsn_upto = InvalidXLogRecPtr; + shared->done = false; + SharedFileSetInit(&shared->sfs, seg); + shared->last_exported = -1; + SpinLockInit(&shared->mutex); + shared->dbid = MyDatabaseId; + + /* + * This is the UserId set in cluster_rel(). Security context shouldn't be + * needed for decoding worker. + */ + shared->roleid = GetUserId(); + shared->relid = relid; + ConditionVariableInit(&shared->cv); + shared->backend_proc = MyProc; + shared->backend_pid = MyProcPid; + shared->backend_proc_number = MyProcNumber; + + mq = shm_mq_create((char *) BUFFERALIGN(shared->error_queue), + REPACK_ERROR_QUEUE_SIZE); + shm_mq_set_receiver(mq, MyProc); + mqh = shm_mq_attach(mq, seg, NULL); + + memset(&bgw, 0, sizeof(bgw)); + snprintf(bgw.bgw_name, BGW_MAXLEN, + "REPACK decoding worker for relation \"%s\"", + get_rel_name(relid)); + snprintf(bgw.bgw_type, BGW_MAXLEN, "REPACK decoding worker"); + bgw.bgw_flags = BGWORKER_SHMEM_ACCESS | + BGWORKER_BACKEND_DATABASE_CONNECTION; + bgw.bgw_start_time = BgWorkerStart_RecoveryFinished; + bgw.bgw_restart_time = BGW_NEVER_RESTART; + snprintf(bgw.bgw_library_name, MAXPGPATH, "postgres"); + snprintf(bgw.bgw_function_name, BGW_MAXLEN, "RepackWorkerMain"); + bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); + bgw.bgw_notify_pid = MyProcPid; + + decoding_worker = palloc0_object(DecodingWorker); + if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) + ereport(ERROR, + (errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), + errmsg("out of background worker slots"), + errhint("You might need to increase \"%s\".", "max_worker_processes"))); + + decoding_worker->seg = seg; + decoding_worker->error_mqh = mqh; + + /* + * The decoding setup must be done before the caller can have XID assigned + * for any reason, otherwise the worker might end up in a deadlock, + * waiting for the caller's transaction to end. Therefore wait here until + * the worker indicates that it has the logical decoding initialized. + */ + ConditionVariablePrepareToSleep(&shared->cv); + for (;;) + { + int initialized; + + SpinLockAcquire(&shared->mutex); + initialized = shared->initialized; + SpinLockRelease(&shared->mutex); + + if (initialized) + break; + + ConditionVariableSleep(&shared->cv, WAIT_EVENT_REPACK_WORKER_EXPORT); + } + ConditionVariableCancelSleep(); +} + +/* + * Stop the decoding worker and cleanup the related resources. + * + * The worker stops on its own when it knows there is no more work to do, but + * we need to stop it explicitly at least on ERROR in the launching backend. + */ +static void +stop_decoding_worker(void) +{ + BgwHandleStatus status; + + /* Haven't reached the worker startup? */ + if (decoding_worker == NULL) + return; + + /* Could not register the worker? */ + if (decoding_worker->handle == NULL) + return; + + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); + + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + (errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command"))); + + shm_mq_detach(decoding_worker->error_mqh); + + /* + * If we could not cancel the current sleep due to ERROR, do that before + * we detach from the shared memory the condition variable is located in. + * If we did not, the bgworker ERROR handling code would try and fail + * badly. + */ + ConditionVariableCancelSleep(); + + dsm_detach(decoding_worker->seg); + pfree(decoding_worker); + decoding_worker = NULL; +} + +/* Is this process a REPACK worker? */ +static bool is_repack_worker = false; + +static pid_t backend_pid; +static ProcNumber backend_proc_number; + +/* + * See ParallelWorkerShutdown for details. + */ +static void +RepackWorkerShutdown(int code, Datum arg) +{ + SendProcSignal(backend_pid, + PROCSIG_REPACK_MESSAGE, + backend_proc_number); + + dsm_detach((dsm_segment *) DatumGetPointer(arg)); +} + +/* REPACK decoding worker entry point */ +void +RepackWorkerMain(Datum main_arg) +{ + dsm_segment *seg; + DecodingWorkerShared *shared; + shm_mq *mq; + shm_mq_handle *mqh; + + is_repack_worker = true; + + /* + * Override the default bgworker_die() with die() so we can use + * CHECK_FOR_INTERRUPTS(). + */ + pqsignal(SIGTERM, die); + BackgroundWorkerUnblockSignals(); + + seg = dsm_attach(DatumGetUInt32(main_arg)); + if (seg == NULL) + ereport(ERROR, + (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE), + errmsg("could not map dynamic shared memory segment"))); + + shared = (DecodingWorkerShared *) dsm_segment_address(seg); + + /* Arrange to signal the leader if we exit. */ + backend_pid = shared->backend_pid; + backend_proc_number = shared->backend_proc_number; + before_shmem_exit(RepackWorkerShutdown, PointerGetDatum(seg)); + + /* + * Join locking group - see the comments around the call of + * start_decoding_worker(). + */ + if (!BecomeLockGroupMember(shared->backend_proc, backend_pid)) + /* The leader is not running anymore. */ + return; + + /* + * Setup a queue to send error messages to the backend that launched this + * worker. + */ + mq = (shm_mq *) (char *) BUFFERALIGN(shared->error_queue); + shm_mq_set_sender(mq, MyProc); + mqh = shm_mq_attach(mq, seg, NULL); + pq_redirect_to_shm_mq(seg, mqh); + pq_set_parallel_leader(shared->backend_pid, + shared->backend_proc_number); + + /* Connect to the database. */ + BackgroundWorkerInitializeConnectionByOid(shared->dbid, shared->roleid, 0); + + repack_worker_internal(seg); +} + +static void +repack_worker_internal(dsm_segment *seg) +{ + DecodingWorkerShared *shared; + LogicalDecodingContext *decoding_ctx; + SharedFileSet *sfs; + Snapshot snapshot; + + /* + * Transaction is needed to open relation, and it also provides us with a + * resource owner. + */ + StartTransactionCommand(); + + shared = (DecodingWorkerShared *) dsm_segment_address(seg); + + /* + * Not sure the spinlock is needed here - the backend should not change + * anything in the shared memory until we have serialized the snapshot. + */ + SpinLockAcquire(&shared->mutex); + Assert(XLogRecPtrIsInvalid(shared->lsn_upto)); + sfs = &shared->sfs; + SpinLockRelease(&shared->mutex); + + SharedFileSetAttach(sfs, seg); + + /* + * Prepare to capture the concurrent data changes ourselves. + */ + decoding_ctx = setup_logical_decoding(shared->relid); + + /* Announce that we're ready. */ + SpinLockAcquire(&shared->mutex); + shared->initialized = true; + SpinLockRelease(&shared->mutex); + ConditionVariableSignal(&shared->cv); + + /* Build the initial snapshot and export it. */ + snapshot = SnapBuildInitialSnapshotForRepack(decoding_ctx->snapshot_builder); + export_initial_snapshot(snapshot, shared); + + /* + * Only historic snapshots should be used now. Do not let us restrict the + * progress of xmin horizon. + */ + InvalidateCatalogSnapshot(); + + while (!decode_concurrent_changes(decoding_ctx, shared)) + ; + + /* Cleanup. */ + cleanup_logical_decoding(decoding_ctx); + CommitTransactionCommand(); +} + +/* + * Make snapshot available to the backend that launched the decoding worker. + */ +static void +export_initial_snapshot(Snapshot snapshot, DecodingWorkerShared *shared) +{ + char fname[MAXPGPATH]; + BufFile *file; + Size snap_size; + char *snap_space; + + snap_size = EstimateSnapshotSpace(snapshot); + snap_space = (char *) palloc(snap_size); + SerializeSnapshot(snapshot, snap_space); + FreeSnapshot(snapshot); + + DecodingWorkerFileName(fname, shared->relid, shared->last_exported + 1); + file = BufFileCreateFileSet(&shared->sfs.fs, fname); + /* To make restoration easier, write the snapshot size first. */ + BufFileWrite(file, &snap_size, sizeof(snap_size)); + BufFileWrite(file, snap_space, snap_size); + pfree(snap_space); + BufFileClose(file); + + /* Increase the counter to tell the backend that the file is available. */ + SpinLockAcquire(&shared->mutex); + shared->last_exported++; + SpinLockRelease(&shared->mutex); + ConditionVariableSignal(&shared->cv); +} + +/* + * Get the initial snapshot from the decoding worker. + */ +static Snapshot +get_initial_snapshot(DecodingWorker *worker) +{ + DecodingWorkerShared *shared; + char fname[MAXPGPATH]; + BufFile *file; + Size snap_size; + char *snap_space; + Snapshot snapshot; + + shared = (DecodingWorkerShared *) dsm_segment_address(worker->seg); + + /* + * The worker needs to initialize the logical decoding, which usually + * takes some time. Therefore it makes sense to prepare for the sleep + * first. + */ + ConditionVariablePrepareToSleep(&shared->cv); + for (;;) + { + int last_exported; + + SpinLockAcquire(&shared->mutex); + last_exported = shared->last_exported; + SpinLockRelease(&shared->mutex); + + /* + * Has the worker exported the file we are waiting for? + */ + if (last_exported == WORKER_FILE_SNAPSHOT) + break; + + ConditionVariableSleep(&shared->cv, WAIT_EVENT_REPACK_WORKER_EXPORT); + } + ConditionVariableCancelSleep(); + + /* Read the snapshot from a file. */ + DecodingWorkerFileName(fname, shared->relid, WORKER_FILE_SNAPSHOT); + file = BufFileOpenFileSet(&shared->sfs.fs, fname, O_RDONLY, false); + BufFileReadExact(file, &snap_size, sizeof(snap_size)); + snap_space = (char *) palloc(snap_size); + BufFileReadExact(file, snap_space, snap_size); + BufFileClose(file); + + /* Restore it. */ + snapshot = RestoreSnapshot(snap_space); + pfree(snap_space); + + return snapshot; +} + +bool +IsRepackWorker(void) +{ + return is_repack_worker; +} + +/* + * Handle receipt of an interrupt indicating a repack worker message. + * + * Note: this is called within a signal handler! All we can do is set + * a flag that will cause the next CHECK_FOR_INTERRUPTS() to invoke + * ProcessRepackMessages(). + */ +void +HandleRepackMessageInterrupt(void) +{ + InterruptPending = true; + RepackMessagePending = true; + SetLatch(MyLatch); +} + +/* + * Process any queued protocol messages received from parallel workers. + */ +void +ProcessRepackMessages(void) +{ + MemoryContext oldcontext; + + static MemoryContext hpm_context = NULL; + + /* + * Nothing to do if we haven't launched the worker yet or have already + * terminated it. + */ + if (decoding_worker == NULL) + return; + + /* + * This is invoked from ProcessInterrupts(), and since some of the + * functions it calls contain CHECK_FOR_INTERRUPTS(), there is a potential + * for recursive calls if more signals are received while this runs. It's + * unclear that recursive entry would be safe, and it doesn't seem useful + * even if it is safe, so let's block interrupts until done. + */ + HOLD_INTERRUPTS(); + + /* + * Moreover, CurrentMemoryContext might be pointing almost anywhere. We + * don't want to risk leaking data into long-lived contexts, so let's do + * our work here in a private context that we can reset on each use. + */ + if (hpm_context == NULL) /* first time through? */ + hpm_context = AllocSetContextCreate(TopMemoryContext, + "ProcessRepackMessages", + ALLOCSET_DEFAULT_SIZES); + else + MemoryContextReset(hpm_context); + + oldcontext = MemoryContextSwitchTo(hpm_context); + + /* OK to process messages. Reset the flag saying there are more to do. */ + RepackMessagePending = false; + + /* + * Read as many messages as we can from each worker, but stop when no more + * messages can be read from the worker without blocking. + */ + while (true) + { + shm_mq_result res; + Size nbytes; + void *data; + + res = shm_mq_receive(decoding_worker->error_mqh, &nbytes, + &data, true); + if (res == SHM_MQ_WOULD_BLOCK) + break; + else if (res == SHM_MQ_SUCCESS) + { + StringInfoData msg; + + initStringInfo(&msg); + appendBinaryStringInfo(&msg, data, nbytes); + ProcessRepackMessage(&msg); + pfree(msg.data); + } + else + { + /* + * The decoding worker is special in that it exits as soon as it + * has its work done. Thus the DETACHED result code is fine. + */ + Assert(res == SHM_MQ_DETACHED); + + break; + } + } + + MemoryContextSwitchTo(oldcontext); + + /* Might as well clear the context on our way out */ + MemoryContextReset(hpm_context); + + RESUME_INTERRUPTS(); +} + +/* + * Process a single protocol message received from a single parallel worker. + */ +static void +ProcessRepackMessage(StringInfo msg) +{ + char msgtype; + + msgtype = pq_getmsgbyte(msg); + + switch (msgtype) + { + case PqMsg_ErrorResponse: + case PqMsg_NoticeResponse: + { + ErrorData edata; + + /* Parse ErrorResponse or NoticeResponse. */ + pq_parse_errornotice(msg, &edata); + + /* Death of a worker isn't enough justification for suicide. */ + edata.elevel = Min(edata.elevel, ERROR); + + /* + * If desired, add a context line to show that this is a + * message propagated from a parallel worker. Otherwise, it + * can sometimes be confusing to understand what actually + * happened. + */ + if (edata.context) + edata.context = psprintf("%s\n%s", edata.context, + _("decoding worker")); + else + edata.context = pstrdup(_("decoding worker")); + + /* Rethrow error or print notice. */ + ThrowErrorData(&edata); + + break; + } + + default: + { + elog(ERROR, "unrecognized message type received from decoding worker: %c (message length %d bytes)", + msgtype, msg->len); + } + } +} diff --git a/src/backend/libpq/pqmq.c b/src/backend/libpq/pqmq.c index 6e4bbfb5aa1..42f6fa472c5 100644 --- a/src/backend/libpq/pqmq.c +++ b/src/backend/libpq/pqmq.c @@ -14,6 +14,7 @@ #include "postgres.h" #include "access/parallel.h" +#include "commands/cluster.h" #include "libpq/libpq.h" #include "libpq/pqformat.h" #include "libpq/pqmq.h" @@ -175,6 +176,10 @@ mq_putmessage(char msgtype, const char *s, size_t len) SendProcSignal(pq_mq_parallel_leader_pid, PROCSIG_PARALLEL_APPLY_MESSAGE, pq_mq_parallel_leader_proc_number); + else if (IsRepackWorker()) + SendProcSignal(pq_mq_parallel_leader_pid, + PROCSIG_REPACK_MESSAGE, + pq_mq_parallel_leader_proc_number); else { Assert(IsParallelWorker()); diff --git a/src/backend/postmaster/bgworker.c b/src/backend/postmaster/bgworker.c index 65deabe91a7..334bb708c5b 100644 --- a/src/backend/postmaster/bgworker.c +++ b/src/backend/postmaster/bgworker.c @@ -13,6 +13,7 @@ #include "postgres.h" #include "access/parallel.h" +#include "commands/cluster.h" #include "libpq/pqsignal.h" #include "miscadmin.h" #include "pgstat.h" @@ -136,6 +137,9 @@ static const struct }, { "SequenceSyncWorkerMain", SequenceSyncWorkerMain + }, + { + "RepackWorkerMain", RepackWorkerMain } }; diff --git a/src/backend/replication/logical/logical.c b/src/backend/replication/logical/logical.c index b0ef1a12520..35a46988285 100644 --- a/src/backend/replication/logical/logical.c +++ b/src/backend/replication/logical/logical.c @@ -194,7 +194,11 @@ StartupDecodingContext(List *output_plugin_options, ctx->slot = slot; - ctx->reader = XLogReaderAllocate(wal_segment_size, NULL, xl_routine, ctx); + /* + * TODO A separate patch for PG core, unless there's really a reason to + * pass ctx for private_data (May extensions expect ctx?). + */ + ctx->reader = XLogReaderAllocate(wal_segment_size, NULL, xl_routine, NULL); if (!ctx->reader) ereport(ERROR, (errcode(ERRCODE_OUT_OF_MEMORY), diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index c8930640a0d..fb9956d392d 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -168,17 +168,13 @@ store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; - char *change_raw; - ConcurrentChange change; + char kind_byte = (char) kind; bool flattened = false; - Size size; - Datum values[1]; - bool isnull[1]; - char *dst; dstate = (RepackDecodingState *) ctx->output_writer_private; - size = VARHDRSZ + SizeOfConcurrentChange; + /* Store the change kind. */ + BufFileWrite(dstate->file, &kind_byte, 1); /* * ReorderBufferCommit() stores the TOAST chunks in its private memory @@ -195,46 +191,12 @@ store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, tuple = toast_flatten_tuple(tuple, dstate->tupdesc); flattened = true; } + /* Store the tuple size ... */ + BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); - size += tuple->t_len; - if (size >= MaxAllocSize) - elog(ERROR, "Change is too big."); - - /* Construct the change. */ - change_raw = (char *) palloc0(size); - SET_VARSIZE(change_raw, size); - - /* - * Since the varlena alignment might not be sufficient for the structure, - * set the fields in a local instance and remember where it should - * eventually be copied. - */ - change.kind = kind; - dst = (char *) VARDATA(change_raw); - - /* - * Copy the tuple. - * - * Note: change->tup_data.t_data must be fixed on retrieval! - */ - memcpy(&change.tup_data, tuple, sizeof(HeapTupleData)); - memcpy(dst, &change, SizeOfConcurrentChange); - dst += SizeOfConcurrentChange; - memcpy(dst, tuple->t_data, tuple->t_len); - - /* The data has been copied. */ + /* Free the flat copy if created above. */ if (flattened) pfree(tuple); - - /* Store as tuple of 1 bytea column. */ - values[0] = PointerGetDatum(change_raw); - isnull[0] = false; - tuplestore_putvalues(dstate->tstore, dstate->tupdesc_change, - values, isnull); - - /* Accounting. */ - dstate->nchanges++; - - /* Cleanup. */ - pfree(change_raw); } diff --git a/src/backend/storage/ipc/procsignal.c b/src/backend/storage/ipc/procsignal.c index 8e56922dcea..6f9e7a7aab7 100644 --- a/src/backend/storage/ipc/procsignal.c +++ b/src/backend/storage/ipc/procsignal.c @@ -19,6 +19,7 @@ #include "access/parallel.h" #include "commands/async.h" +#include "commands/cluster.h" #include "miscadmin.h" #include "pgstat.h" #include "port/pg_bitutils.h" @@ -697,6 +698,9 @@ procsignal_sigusr1_handler(SIGNAL_ARGS) if (CheckProcSignal(PROCSIG_PARALLEL_APPLY_MESSAGE)) HandleParallelApplyMessageInterrupt(); + if (CheckProcSignal(PROCSIG_REPACK_MESSAGE)) + HandleRepackMessageInterrupt(); + if (CheckProcSignal(PROCSIG_RECOVERY_CONFLICT_DATABASE)) HandleRecoveryConflictInterrupt(PROCSIG_RECOVERY_CONFLICT_DATABASE); diff --git a/src/backend/tcop/postgres.c b/src/backend/tcop/postgres.c index 015c67bbeba..566e5a50c30 100644 --- a/src/backend/tcop/postgres.c +++ b/src/backend/tcop/postgres.c @@ -36,6 +36,7 @@ #include "access/xact.h" #include "catalog/pg_type.h" #include "commands/async.h" +#include "commands/cluster.h" #include "commands/event_trigger.h" #include "commands/explain_state.h" #include "commands/prepare.h" @@ -3541,6 +3542,9 @@ ProcessInterrupts(void) if (ParallelApplyMessagePending) ProcessParallelApplyMessages(); + + if (RepackMessagePending) + ProcessRepackMessages(); } /* diff --git a/src/backend/utils/activity/wait_event_names.txt b/src/backend/utils/activity/wait_event_names.txt index 3299de23bb3..73a3def69bc 100644 --- a/src/backend/utils/activity/wait_event_names.txt +++ b/src/backend/utils/activity/wait_event_names.txt @@ -62,6 +62,7 @@ LOGICAL_APPLY_MAIN "Waiting in main loop of logical replication apply process." LOGICAL_LAUNCHER_MAIN "Waiting in main loop of logical replication launcher process." LOGICAL_PARALLEL_APPLY_MAIN "Waiting in main loop of logical replication parallel apply process." RECOVERY_WAL_STREAM "Waiting in main loop of startup process for WAL to arrive, during streaming recovery." +REPACK_WORKER_MAIN "Waiting in main loop of REPACK decoding worker process." REPLICATION_SLOTSYNC_MAIN "Waiting in main loop of slot synchronization." REPLICATION_SLOTSYNC_SHUTDOWN "Waiting for slot sync worker to shut down." SYSLOGGER_MAIN "Waiting in main loop of syslogger process." @@ -154,6 +155,7 @@ RECOVERY_CONFLICT_SNAPSHOT "Waiting for recovery conflict resolution for a vacuu RECOVERY_CONFLICT_TABLESPACE "Waiting for recovery conflict resolution for dropping a tablespace." RECOVERY_END_COMMAND "Waiting for <xref linkend="guc-recovery-end-command"/> to complete." RECOVERY_PAUSE "Waiting for recovery to be resumed." +REPACK_WORKER_EXPORT "Waiting for decoding worker to export a new output file." REPLICATION_ORIGIN_DROP "Waiting for a replication origin to become inactive so it can be dropped." REPLICATION_SLOT_DROP "Waiting for a replication slot to become inactive so it can be dropped." RESTORE_COMMAND "Waiting for <xref linkend="guc-restore-command"/> to complete." diff --git a/src/include/access/tableam.h b/src/include/access/tableam.h index 76aa993009a..15760363a1a 100644 --- a/src/include/access/tableam.h +++ b/src/include/access/tableam.h @@ -22,7 +22,6 @@ #include "access/xact.h" #include "commands/vacuum.h" #include "executor/tuptable.h" -#include "replication/logical.h" #include "storage/read_stream.h" #include "utils/rel.h" #include "utils/snapshot.h" @@ -631,7 +630,6 @@ typedef struct TableAmRoutine bool use_sort, TransactionId OldestXmin, Snapshot snapshot, - LogicalDecodingContext *decoding_ctx, TransactionId *xid_cutoff, MultiXactId *multi_cutoff, double *num_tuples, @@ -1651,8 +1649,6 @@ table_relation_copy_data(Relation rel, const RelFileLocator *newrlocator) * - *multi_cutoff - ditto * - snapshot - if != NULL, ignore data changes done by transactions that this * (MVCC) snapshot considers still in-progress or in the future. - * - decoding_ctx - logical decoding context, to capture concurrent data - * changes. * * Output parameters: * - *xid_cutoff - rel's new relfrozenxid value, may be invalid @@ -1666,7 +1662,6 @@ table_relation_copy_for_cluster(Relation OldTable, Relation NewTable, bool use_sort, TransactionId OldestXmin, Snapshot snapshot, - LogicalDecodingContext *decoding_ctx, TransactionId *xid_cutoff, MultiXactId *multi_cutoff, double *num_tuples, @@ -1675,7 +1670,7 @@ table_relation_copy_for_cluster(Relation OldTable, Relation NewTable, { OldTable->rd_tableam->relation_copy_for_cluster(OldTable, NewTable, OldIndex, use_sort, OldestXmin, - snapshot, decoding_ctx, + snapshot, xid_cutoff, multi_cutoff, num_tuples, tups_vacuumed, tups_recently_dead); diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 6a5c476294a..1b05d5d418b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -17,11 +17,13 @@ #include "nodes/parsenodes.h" #include "parser/parse_node.h" #include "replication/decode.h" +#include "postmaster/bgworker.h" #include "replication/logical.h" +#include "storage/buffile.h" #include "storage/lock.h" +#include "storage/shm_mq.h" #include "utils/relcache.h" #include "utils/resowner.h" -#include "utils/tuplestore.h" /* flag bits for ClusterParams->options */ @@ -44,6 +46,9 @@ typedef struct ClusterParams * The following definitions are used by REPACK CONCURRENTLY. */ +/* + * Stored as a single byte in the output file. + */ typedef enum { CHANGE_INSERT, @@ -52,68 +57,30 @@ typedef enum CHANGE_DELETE } ConcurrentChangeKind; -typedef struct ConcurrentChange -{ - /* See the enum above. */ - ConcurrentChangeKind kind; - - /* - * The actual tuple. - * - * The tuple data follows the ConcurrentChange structure. Before use make - * sure the tuple is correctly aligned (ConcurrentChange can be stored as - * bytea) and that tuple->t_data is fixed. - */ - HeapTupleData tup_data; -} ConcurrentChange; - -#define SizeOfConcurrentChange (offsetof(ConcurrentChange, tup_data) + \ - sizeof(HeapTupleData)) - /* * Logical decoding state. * - * Here we store the data changes that we decode from WAL while the table - * contents is being copied to a new storage. Also the necessary metadata - * needed to apply these changes to the table is stored here. + * The output plugin uses it to store the data changes that it decodes from + * WAL while the table contents is being copied to a new storage. */ typedef struct RepackDecodingState { /* The relation whose changes we're decoding. */ Oid relid; - /* Replication slot name. */ - NameData slotname; - - /* - * Decoded changes are stored here. Although we try to avoid excessive - * batches, it can happen that the changes need to be stored to disk. The - * tuplestore does this transparently. - */ - Tuplestorestate *tstore; - - /* The current number of changes in tstore. */ - double nchanges; - - /* - * Descriptor to store the ConcurrentChange structure serialized (bytea). - * We can't store the tuple directly because tuplestore only supports - * minimum tuple and we may need to transfer OID system column from the - * output plugin. Also we need to transfer the change kind, so it's better - * to put everything in the structure than to use 2 tuplestores "in - * parallel". - */ - TupleDesc tupdesc_change; - - /* Tuple descriptor needed to update indexes. */ + /* Tuple descriptor of the relation being processed. */ TupleDesc tupdesc; - /* Slot to retrieve data from tstore. */ - TupleTableSlot *tsslot; - - ResourceOwner resowner; + /* The current output file. */ + BufFile *file; } RepackDecodingState; +extern PGDLLIMPORT volatile sig_atomic_t RepackMessagePending; + +extern bool IsRepackWorker(void); +extern void HandleRepackMessageInterrupt(void); +extern void ProcessRepackMessages(void); + extern void ExecRepack(ParseState *pstate, RepackStmt *stmt, bool isTopLevel); extern void cluster_rel(RepackCommand command, Relation OldHeap, Oid indexOid, @@ -136,6 +103,6 @@ extern void finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, extern bool am_decoding_for_repack(void); extern bool change_useless_for_repack(XLogRecordBuffer *buf); -extern void repack_decode_concurrent_changes(LogicalDecodingContext *ctx, - XLogRecPtr end_of_wal); + +extern void RepackWorkerMain(Datum main_arg); #endif /* CLUSTER_H */ diff --git a/src/include/storage/procsignal.h b/src/include/storage/procsignal.h index e52b8eb7697..3ef35ca6b80 100644 --- a/src/include/storage/procsignal.h +++ b/src/include/storage/procsignal.h @@ -36,6 +36,7 @@ typedef enum PROCSIG_BARRIER, /* global barrier interrupt */ PROCSIG_LOG_MEMORY_CONTEXT, /* ask backend to log the memory contexts */ PROCSIG_PARALLEL_APPLY_MESSAGE, /* Message from parallel apply workers */ + PROCSIG_REPACK_MESSAGE, /* Message from repack worker */ /* Recovery conflict reasons */ PROCSIG_RECOVERY_CONFLICT_FIRST, diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index a0b7b38a5e2..d1a694f9008 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -496,7 +496,6 @@ CompressFileHandle CompressionLocation CompressorState ComputeXidHorizonsResult -ConcurrentChange ConcurrentChangeKind ConditionVariable ConditionVariableMinimallyPadded @@ -636,6 +635,9 @@ DeclareCursorStmt DecodedBkpBlock DecodedXLogRecord DecodingOutputState +DecodingWorker +DecodingWorkerShared +DecodingWorkerState DefElem DefElemAction DefaultACLInfo -- 2.47.3 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v29-0006-Use-multiple-snapshots-to-copy-the-data.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 5/5] Serialize decoded tuples without flattening. @ 2026-02-27 18:01 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-02-27 18:01 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 260 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 114 ++++++-- src/include/commands/cluster.h | 5 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 318 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index db710259eeb..e4de410e733 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2574,6 +2579,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2624,14 +2630,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2642,18 +2640,23 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2822,10 +2825,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2835,6 +2838,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2849,14 +2860,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2868,7 +2872,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2892,18 +2896,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2920,6 +2934,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3030,6 +3045,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3458,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..8e22aeb163b 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,94 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + else + natt_ext = 0; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + pfree(ext_val); + } + list_free(attrs_ext); + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..a32813e8530 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,10 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; - - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; +#endif /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..f84917daca2 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, wich we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/4] Serialize decoded tuples without flattening. @ 2026-03-02 14:30 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-02 14:30 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 116 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 327 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..06cb252ddbd 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,98 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + MemoryContextSwitchTo(oldcxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-=-- ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-05 18:58 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-05 18:58 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index 6c99b65247d..e0dd33b52ed 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2586,6 +2591,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2636,14 +2642,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2654,18 +2652,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2834,10 +2841,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2847,6 +2854,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2861,14 +2876,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2880,7 +2888,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2904,18 +2912,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2932,6 +2950,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3263,15 +3462,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v38-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 118 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 329 insertions(+), 67 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dd1a7473cdf..2adce59b0fa 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -35,6 +35,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -287,6 +288,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2587,6 +2592,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2637,14 +2643,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2655,18 +2653,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2835,10 +2842,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2848,6 +2855,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2862,14 +2877,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2881,7 +2889,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2905,18 +2913,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2933,6 +2951,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3042,6 +3061,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3264,15 +3463,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v39-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH v40 3/4] Serialize decoded tuples without flattening. @ 2026-03-09 10:35 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-09 10:35 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 122 ++++++-- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 331 insertions(+), 69 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..77e301b7c63 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..707940c1127 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -97,9 +97,8 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, dstate = (RepackDecodingState *) ctx->output_writer_private; - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == dstate->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +116,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +131,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +145,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +163,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; - } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); - /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + TupleDesc desc; + Datum *attrs; + bool *isnull; - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); + } + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); + /* ... and the tuple itself. */ + BufFileWrite(file, tuple->t_data, tuple->t_len); + + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --k4rn5ob3nx2ufkij Content-Type: text/x-diff; charset=utf-8 Content-Disposition: attachment; filename="v40-0004-Use-BulkInsertState-when-copying-data-to-the-new.patch" ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/5] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index fe419ef808e..8b5571374d0 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -285,6 +286,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2622,6 +2627,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2672,14 +2678,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2690,18 +2688,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2870,10 +2877,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2883,6 +2890,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2897,14 +2912,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2916,7 +2924,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2940,18 +2948,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2968,6 +2986,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3077,6 +3096,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3299,15 +3498,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v41-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
* [PATCH 4/7] Serialize decoded tuples without flattening. @ 2026-03-11 14:19 Antonin Houska <[email protected]> 0 siblings, 0 replies; 513+ messages in thread From: Antonin Houska @ 2026-03-11 14:19 UTC (permalink / raw) So far we used to flatten the tuples produced by logical decoding in order to write them to a temporary file. That means that all the TOASTed attributes ended up in a single chunk of memory. The problem is that even if individual attributes do fit into the maximum chunk size (currently 1 GB), the whole tuple is not guaranteed to fit. The flattening might be a problem in the future anyway, since there's an effort to restrict the impact of REPACK (CONCURRENTLY) on the VACUUM xmin horizon. However, as the flattening assumes scans of the TOAST relaation, the less we restrict VACUUM, the more likely it is that the TOAST attributes needed for the flattening won't be available at decoding time. (This patch also removes unnecessary field 'tupdesc' from RepackDecodingState and allocates it in the appropriate memory context.) --- src/backend/commands/cluster.c | 264 +++++++++++++++--- .../pgoutput_repack/pgoutput_repack.c | 123 +++++--- src/include/commands/cluster.h | 6 +- .../expected/repack_toast.out | 1 + .../injection_points/specs/repack_toast.spec | 7 + 5 files changed, 330 insertions(+), 71 deletions(-) diff --git a/src/backend/commands/cluster.c b/src/backend/commands/cluster.c index dcad236bd0a..d89be1b9533 100644 --- a/src/backend/commands/cluster.c +++ b/src/backend/commands/cluster.c @@ -33,6 +33,7 @@ #include "postgres.h" #include "access/amapi.h" +#include "access/detoast.h" #include "access/heapam.h" #include "access/multixact.h" #include "access/relscan.h" @@ -286,6 +287,10 @@ static void apply_concurrent_update(Relation rel, HeapTuple tup, IndexInsertState *iistate, TupleTableSlot *index_slot); static void apply_concurrent_delete(Relation rel, HeapTuple tup_target); +static HeapTuple restore_tuple(BufFile *file, Relation relation, + MemoryContext cxt); +static HeapTuple adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt); static HeapTuple find_target_tuple(Relation rel, ChangeDest *dest, HeapTuple tup_key, TupleTableSlot *ident_slot); @@ -2619,6 +2624,7 @@ setup_logical_decoding(Oid relid) LogicalDecodingContext *ctx; NameData slotname; RepackDecodingState *dstate; + MemoryContext oldcxt; /* * REPACK CONCURRENTLY is not allowed in a transaction block, so this @@ -2669,14 +2675,6 @@ setup_logical_decoding(Oid relid) */ ctx->reader->routine.page_read = read_local_xlog_page_no_wait; - /* - * read_local_xlog_page_no_wait() needs to be able to indicate the end of - * WAL. - */ - ctx->reader->private_data = MemoryContextAllocZero(ctx->context, - sizeof(ReadLocalXLogPageNoWaitPrivate)); - - /* Some WAL records should have been read. */ Assert(ctx->reader->EndRecPtr != InvalidXLogRecPtr); @@ -2687,18 +2685,27 @@ setup_logical_decoding(Oid relid) XLByteToSeg(ctx->reader->EndRecPtr, repack_current_segment, wal_segment_size); - dstate = palloc0_object(RepackDecodingState); - dstate->relid = relid; + /* Our private state belongs to the decoding context. */ + oldcxt = MemoryContextSwitchTo(ctx->context); /* - * Tuple descriptor may be needed to flatten a tuple before we write it to - * a file. A copy is needed because the decoding worker invalidates system - * caches before it starts to do the actual work. + * read_local_xlog_page_no_wait() needs to be able to indicate the end of + * WAL. */ - rel = table_open(relid, AccessShareLock); - dstate->tupdesc = CreateTupleDescCopy(RelationGetDescr(rel)); + ctx->reader->private_data = palloc0_object(ReadLocalXLogPageNoWaitPrivate); + dstate = palloc0_object(RepackDecodingState); + MemoryContextSwitchTo(oldcxt); + +#ifdef USE_ASSERT_CHECKING + dstate->relid = relid; +#endif + + dstate->change_cxt = AllocSetContextCreate(ctx->context, + "REPACK - change", + ALLOCSET_DEFAULT_SIZES); /* Avoid logical decoding of other relations. */ + rel = table_open(relid, AccessShareLock); repacked_rel_locator = rel->rd_locator; toastrelid = rel->rd_rel->reltoastrelid; if (OidIsValid(toastrelid)) @@ -2867,10 +2874,10 @@ static void apply_concurrent_changes(BufFile *file, ChangeDest *dest) { char kind; - uint32 t_len; Relation rel = dest->rel; TupleTableSlot *index_slot, *ident_slot; + MemoryContext apply_cxt; HeapTuple tup_old = NULL; /* TupleTableSlot is needed to pass the tuple to ExecInsertIndexTuples(). */ @@ -2880,6 +2887,14 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) /* A slot to fetch tuples from identity index. */ ident_slot = table_slot_create(rel, NULL); + /* + * Use a separate memory context for the tuples and any memory needed to + * process them. + */ + apply_cxt = AllocSetContextCreate(TopTransactionContext, + "REPACK - apply", + ALLOCSET_DEFAULT_SIZES); + while (true) { size_t nread; @@ -2894,14 +2909,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) break; /* Read the tuple. */ - BufFileReadExact(file, &t_len, sizeof(t_len)); - tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); - tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); - BufFileReadExact(file, tup->t_data, t_len); - tup->t_len = t_len; - ItemPointerSetInvalid(&tup->t_self); - tup->t_tableOid = RelationGetRelid(dest->rel); - + tup = restore_tuple(file, rel, apply_cxt); if (kind == CHANGE_UPDATE_OLD) { Assert(tup_old == NULL); @@ -2913,7 +2921,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) apply_concurrent_insert(rel, tup, dest->iistate, index_slot); - pfree(tup); + MemoryContextReset(apply_cxt); } else if (kind == CHANGE_UPDATE_NEW || kind == CHANGE_DELETE) { @@ -2937,18 +2945,28 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) elog(ERROR, "failed to find target tuple"); if (kind == CHANGE_UPDATE_NEW) + { + /* + * If 'tup' contains TOAST pointers, they point to the old + * relation's toast. Copy the corresponding TOAST pointers for + * the new relation from the existing tuple. (The fact that we + * received a TOAST pointer here implies that the attribute + * hasn't changed.) + */ + if (HeapTupleHasExternal(tup)) + tup = adjust_toast_pointers(rel, tup, tup_exist, + apply_cxt); + apply_concurrent_update(rel, tup, tup_exist, dest->iistate, index_slot); + } else apply_concurrent_delete(rel, tup_exist); if (tup_old != NULL) - { - pfree(tup_old); tup_old = NULL; - } - pfree(tup); + MemoryContextReset(apply_cxt); } else elog(ERROR, "unrecognized kind of change: %d", kind); @@ -2965,6 +2983,7 @@ apply_concurrent_changes(BufFile *file, ChangeDest *dest) } /* Cleanup. */ + MemoryContextDelete(apply_cxt); ExecDropSingleTupleTableSlot(index_slot); ExecDropSingleTupleTableSlot(ident_slot); } @@ -3074,6 +3093,186 @@ apply_concurrent_delete(Relation rel, HeapTuple tup_target) pgstat_progress_incr_param(PROGRESS_REPACK_HEAP_TUPLES_DELETED, 1); } +/* + * Read tuple from file and store it in given memory context. + * + * External attributes are stored in separate memory chunks, in order to avoid + * exceeding MaxAllocSize - that could happen if the individual attributes are + * smaller than MaxAllocSize but the whole tuple is bigger. + */ +static HeapTuple +restore_tuple(BufFile *file, Relation relation, MemoryContext cxt) +{ + uint32 t_len; + HeapTuple tup; + MemoryContext oldcxt; + uint32 natt_ext; + List *attrs_ext = NIL; + + oldcxt = MemoryContextSwitchTo(cxt); + + /* First, read the external attributes if there are some. */ + BufFileReadExact(file, &natt_ext, sizeof(natt_ext)); + for (int i = 0; i < natt_ext; i++) + { + alignas(uint32) varlena varhdr; + char *ext_val; + Size ext_val_size; + + /* + * Read the header into properly aligned memory before accessing it. + */ + BufFileReadExact(file, &varhdr, VARHDRSZ); + ext_val_size = VARSIZE_ANY(&varhdr); + ext_val = palloc0(ext_val_size); + memcpy(ext_val, &varhdr, VARHDRSZ); + BufFileReadExact(file, ext_val + VARHDRSZ, ext_val_size - VARHDRSZ); + + attrs_ext = lappend(attrs_ext, ext_val); + } + + /* Read the tuple. */ + BufFileReadExact(file, &t_len, sizeof(t_len)); + tup = (HeapTuple) palloc(HEAPTUPLESIZE + t_len); + tup->t_data = (HeapTupleHeader) ((char *) tup + HEAPTUPLESIZE); + BufFileReadExact(file, tup->t_data, t_len); + tup->t_len = t_len; + ItemPointerSetInvalid(&tup->t_self); + tup->t_tableOid = RelationGetRelid(relation); + + /* + * If there are "external indirect" attributes, make the tuple reference + * them. + */ + if (natt_ext > 0) + { + TupleDesc desc; + Datum *attrs; + bool *isnull; + ListCell *lc; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup, desc, attrs, isnull); + + lc = list_head(attrs_ext); + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer, + *new_datum; + varatt_indirect redirect_pointer; + + /* Find the external attributes, like in store_change(). */ + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull[i]) + continue; + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + if (!VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + continue; + + /* Update the attribute. */ + memset(&redirect_pointer, 0, sizeof(redirect_pointer)); + redirect_pointer.pointer = lfirst(lc); + + new_datum = (varlena *) palloc0(INDIRECT_POINTER_SIZE); + SET_VARTAG_EXTERNAL(new_datum, VARTAG_INDIRECT); + memcpy(VARDATA_EXTERNAL(new_datum), &redirect_pointer, + sizeof(redirect_pointer)); + + attrs[i] = PointerGetDatum(new_datum); + + lc = lnext(attrs_ext, lc); + } + Assert(lc == NULL); + + tup = heap_form_tuple(desc, attrs, isnull); + } + + MemoryContextSwitchTo(oldcxt); + + return tup; +} + +/* + * Copy TOAST pointers from 'tup_src' to 'tup_dst' and return the modified + * 'tup_dst'. Use 'cxt' for all memory allocations. + */ +static HeapTuple +adjust_toast_pointers(Relation relation, HeapTuple tup_dst, + HeapTuple tup_src, MemoryContext cxt) +{ + TupleDesc desc; + Datum *attrs_dst; + bool *isnull_dst; + Datum *attrs_src = NULL; + bool *isnull_src = NULL; + MemoryContext oldcxt; + HeapTuple result; + + oldcxt = MemoryContextSwitchTo(cxt); + + desc = RelationGetDescr(relation); + attrs_dst = palloc0_array(Datum, desc->natts); + isnull_dst = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_dst, desc, attrs_dst, isnull_dst); + + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_dst, + *varlena_src; + + if (attr->attisdropped) + continue; + if (attr->attlen != -1) + continue; + if (isnull_dst[i]) + continue; + + varlena_dst = (varlena *) DatumGetPointer(attrs_dst[i]); + if (!VARATT_IS_EXTERNAL_ONDISK(varlena_dst)) + continue; + + /* + * The first TOAST pointer? The caller can easily check if the tuple + * has external attributes(s) in general, but is not supposed to check + * specifically for TOAST. + */ + if (attrs_src == NULL) + { + attrs_src = palloc0_array(Datum, desc->natts); + isnull_src = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tup_src, desc, attrs_src, isnull_src); + } + + varlena_src = (varlena *) DatumGetPointer(attrs_src[i]); + + /* + * Logical decoding only uses TOAST pointer for attributes that + * haven't changed. + */ + Assert(!isnull_src[i]); + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_src)); + + /* Copy the pointer. */ + memcpy(VARDATA_EXTERNAL(varlena_dst), VARDATA_EXTERNAL(varlena_src), + sizeof(varatt_external)); + } + result = heap_form_tuple(desc, attrs_dst, isnull_dst); + + MemoryContextSwitchTo(oldcxt); + + return result; +} + /* * Find the tuple to be updated or deleted. * @@ -3296,15 +3495,8 @@ free_index_insert_state(IndexInsertState *iistate) static void cleanup_logical_decoding(LogicalDecodingContext *ctx) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - FreeTupleDesc(dstate->tupdesc); FreeDecodingContext(ctx); - ReplicationSlotDropAcquired(); - pfree(dstate); } /* diff --git a/src/backend/replication/pgoutput_repack/pgoutput_repack.c b/src/backend/replication/pgoutput_repack/pgoutput_repack.c index d0c464a98d5..90f3a8975b9 100644 --- a/src/backend/replication/pgoutput_repack/pgoutput_repack.c +++ b/src/backend/replication/pgoutput_repack/pgoutput_repack.c @@ -12,7 +12,7 @@ */ #include "postgres.h" -#include "access/heaptoast.h" +#include "access/detoast.h" #include "commands/cluster.h" #include "replication/snapbuild.h" #include "utils/memutils.h" @@ -28,7 +28,7 @@ static void plugin_commit_txn(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, XLogRecPtr commit_lsn); static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation rel, ReorderBufferChange *change); -static void store_change(LogicalDecodingContext *ctx, +static void store_change(LogicalDecodingContext *ctx, Relation relation, ConcurrentChangeKind kind, HeapTuple tuple); void @@ -93,13 +93,9 @@ static void plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, Relation relation, ReorderBufferChange *change) { - RepackDecodingState *dstate; - - dstate = (RepackDecodingState *) ctx->output_writer_private; - - /* Only interested in one particular relation. */ - if (relation->rd_id != dstate->relid) - return; + /* Changes of other relation should not have been decoded. */ + Assert(RelationGetRelid(relation) == + ((RepackDecodingState *) ctx->output_writer_private)->relid); /* Decode entry depending on its type */ switch (change->action) @@ -117,7 +113,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (newtuple == NULL) elog(ERROR, "incomplete insert info."); - store_change(ctx, CHANGE_INSERT, newtuple); + store_change(ctx, relation, CHANGE_INSERT, newtuple); } break; case REORDER_BUFFER_CHANGE_UPDATE: @@ -132,9 +128,9 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, elog(ERROR, "incomplete update info."); if (oldtuple != NULL) - store_change(ctx, CHANGE_UPDATE_OLD, oldtuple); + store_change(ctx, relation, CHANGE_UPDATE_OLD, oldtuple); - store_change(ctx, CHANGE_UPDATE_NEW, newtuple); + store_change(ctx, relation, CHANGE_UPDATE_NEW, newtuple); } break; case REORDER_BUFFER_CHANGE_DELETE: @@ -146,7 +142,7 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, if (oldtuple == NULL) elog(ERROR, "incomplete delete info."); - store_change(ctx, CHANGE_DELETE, oldtuple); + store_change(ctx, relation, CHANGE_DELETE, oldtuple); } break; default: @@ -164,39 +160,100 @@ plugin_change(LogicalDecodingContext *ctx, ReorderBufferTXN *txn, /* Store concurrent data change. */ static void -store_change(LogicalDecodingContext *ctx, ConcurrentChangeKind kind, - HeapTuple tuple) +store_change(LogicalDecodingContext *ctx, Relation relation, + ConcurrentChangeKind kind, HeapTuple tuple) { RepackDecodingState *dstate; + MemoryContext oldcxt; + BufFile *file; char kind_byte = (char) kind; - bool flattened = false; + List *attrs_ext = NIL; + uint32 natt_ext; dstate = (RepackDecodingState *) ctx->output_writer_private; + file = dstate->file; /* Store the change kind. */ - BufFileWrite(dstate->file, &kind_byte, 1); + BufFileWrite(file, &kind_byte, 1); + + /* Make sure there are no memory leaks. */ + oldcxt = MemoryContextSwitchTo(dstate->change_cxt); /* - * ReorderBufferCommit() stores the TOAST chunks in its private memory - * context and frees them after having called apply_change(). Therefore - * we need flat copy (including TOAST) that we eventually copy into the - * memory context which is available to decode_concurrent_changes(). + * If the tuple contains "external indirect" attributes, we need to write + * the contents to the file because we have no control over that memory. */ if (HeapTupleHasExternal(tuple)) { - /* - * toast_flatten_tuple_to_datum() might be more convenient but we - * don't want the decompression it does. - */ - tuple = toast_flatten_tuple(tuple, dstate->tupdesc); - flattened = true; + TupleDesc desc; + Datum *attrs; + bool *isnull; + + desc = RelationGetDescr(relation); + attrs = palloc0_array(Datum, desc->natts); + isnull = palloc0_array(bool, desc->natts); + + heap_deform_tuple(tuple, desc, attrs, isnull); + + /* First, gather and count the "external indirect" attributes. */ + for (int i = 0; i < desc->natts; i++) + { + CompactAttribute *attr = TupleDescCompactAttr(desc, i); + varlena *varlena_pointer; + + if (attr->attisdropped) + continue; + + /* not a varlena datatype */ + if (attr->attlen != -1) + continue; + + /* no data */ + if (isnull[i]) + continue; + + /* ok, we know we have a toast datum */ + varlena_pointer = (varlena *) DatumGetPointer(attrs[i]); + + if (!VARATT_IS_EXTERNAL(varlena_pointer)) + continue; + + if (VARATT_IS_EXTERNAL_INDIRECT(varlena_pointer)) + attrs_ext = lappend(attrs_ext, varlena_pointer); + else + { + /* + * Logical decoding should not produce "external expanded" + * attributes (those actually should never appear on disk), so + * only TOASTed attribute can be seen here. + */ + Assert(VARATT_IS_EXTERNAL_ONDISK(varlena_pointer)); + } + } + natt_ext = list_length(attrs_ext); } - /* Store the tuple size ... */ - BufFileWrite(dstate->file, &tuple->t_len, sizeof(tuple->t_len)); + else + natt_ext = 0; + + /* Write the number of external attributes. */ + BufFileWrite(file, &natt_ext, sizeof(natt_ext)); + /* ... and the attributes themselves, if there are some. */ + foreach_ptr(varlena, attr_val, attrs_ext) + { + varlena *ext_val; + Size ext_val_size; + + ext_val = detoast_external_attr(attr_val); + ext_val_size = VARSIZE_ANY(ext_val); + BufFileWrite(file, ext_val, ext_val_size); + } + + /* Finally write the tuple size ... */ + BufFileWrite(file, &tuple->t_len, sizeof(tuple->t_len)); /* ... and the tuple itself. */ - BufFileWrite(dstate->file, tuple->t_data, tuple->t_len); + BufFileWrite(file, tuple->t_data, tuple->t_len); - /* Free the flat copy if created above. */ - if (flattened) - pfree(tuple); + /* Cleanup. */ + MemoryContextSwitchTo(oldcxt); + MemoryContextReset(dstate->change_cxt); } diff --git a/src/include/commands/cluster.h b/src/include/commands/cluster.h index 1b05d5d418b..34b7208de9b 100644 --- a/src/include/commands/cluster.h +++ b/src/include/commands/cluster.h @@ -65,11 +65,13 @@ typedef enum */ typedef struct RepackDecodingState { +#ifdef USE_ASSERT_CHECKING /* The relation whose changes we're decoding. */ Oid relid; +#endif - /* Tuple descriptor of the relation being processed. */ - TupleDesc tupdesc; + /* Per-change memory context. */ + MemoryContext change_cxt; /* The current output file. */ BufFile *file; diff --git a/src/test/modules/injection_points/expected/repack_toast.out b/src/test/modules/injection_points/expected/repack_toast.out index 4f866a74e32..b56dde134f8 100644 --- a/src/test/modules/injection_points/expected/repack_toast.out +++ b/src/test/modules/injection_points/expected/repack_toast.out @@ -13,6 +13,7 @@ step change: UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; step check2: INSERT INTO relfilenodes(node) diff --git a/src/test/modules/injection_points/specs/repack_toast.spec b/src/test/modules/injection_points/specs/repack_toast.spec index b48abf21450..b878b198971 100644 --- a/src/test/modules/injection_points/specs/repack_toast.spec +++ b/src/test/modules/injection_points/specs/repack_toast.spec @@ -74,10 +74,17 @@ teardown session s2 step change +# Separately test UPDATE of both plain ("i") and TOASTed ("j") attribute. In +# the first case, the new tuple we get from reorderbuffer.c contains "j" as a +# TOAST pointer, which we need to update so it points to the new heap. In the +# latter case, we receive "j" as "external indirect" value - here we test that +# the decoding worker writes the tuple to a file correctly and that the +# backend executing REPACK manages to restore it. { UPDATE repack_test SET j=get_long_string() where i=2; DELETE FROM repack_test WHERE i=3; INSERT INTO repack_test(i, j) VALUES (4, get_long_string()); + UPDATE repack_test SET i=3 where i=1; } # Check the table from the perspective of s2. step check2 -- 2.47.3 --=-=-= Content-Type: text/x-diff Content-Disposition: attachment; filename=v42-0005-Use-BulkInsertState-when-copying-data-to-the-new-hea.patch ^ permalink raw reply [nested|flat] 513+ messages in thread
end of thread, other threads:[~2026-03-11 14:19 UTC | newest] Thread overview: 513+ messages (download: mbox mbox.gz follow: Atom feed) -- links below jump to the message on this page -- 2022-07-02 05:48 [PATCH] fix "Preserve relfilenodes" for pg_largeobject and its index Justin Pryzby <[email protected]> 2026-01-08 16:47 [PATCH 5/6] Use background worker to do logical decoding. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-02-27 18:01 [PATCH 5/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-02 14:30 [PATCH 4/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-05 18:58 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-09 10:35 [PATCH v40 3/4] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/5] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]> 2026-03-11 14:19 [PATCH 4/7] Serialize decoded tuples without flattening. Antonin Houska <[email protected]>
This inbox is served by agora; see mirroring instructions for how to clone and mirror all data and code used for this inbox